Inverting RANSAC: Global model detection via inlier rate estimation
作者： Roee Litman , Simon Korman , Alex Bronstein , Shai Avidan
DOI: 10.1109/CVPR.2015.7299161
关键词:
摘要: This work presents a novel approach for detecting inliers in given set of correspondences (matches). It does so without explicitly identifying any consensus set, based on method inlier rate estimation (IRE). Given such an estimator the rate, we also present algorithm that detects globally optimal transformation. We provide theoretical analysis IRE using stochastic generative model continuous spaces matches and transformations. allows rigorous investigation limits our case 2D-translation, further giving bounds insights more general case. Our is validated empirically shown to hold practice 2D-affinities. In addition, show combined framework works challenging cases 2D-homography estimation, with very few possibly noisy inliers, where RANSAC generally fails.
sci-hub.se 参考文章(20)
J. Bazin, Hongdong Li, In So Kweon, C. Demonceaux, P. Vasseur, K. Ikeuchi, A Branch-and-Bound Approach to Correspondence and Grouping Problems IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 35, pp. 1565- 1576 ,(2013) , 10.1109/TPAMI.2012.264
Richard Hartley, Andrew Zisserman, Multiple view geometry in computer vision ,(2000)
Andrea Vedaldi, Brian Fulkerson, Vlfeat Proceedings of the international conference on Multimedia - MM '10. pp. 1469- 1472 ,(2010) , 10.1145/1873951.1874249
Martin A. Fischler, Robert C. Bolles, Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography Communications of The ACM. ,vol. 24, pp. 381- 395 ,(1981) , 10.1145/358669.358692
Jiaolong Yang, Hongdong Li, Yunde Jia, None, Go-ICP: Solving 3D Registration Efficiently and Globally Optimally international conference on computer vision. pp. 1457- 1464 ,(2013) , 10.1109/ICCV.2013.184
Carl Olsson, Olof Enqvist, Fredrik Kahl, A polynomial-time bound for matching and registration with outliers computer vision and pattern recognition. pp. 3230- 3237 ,(2008) , 10.1109/CVPR.2008.4587757
O. Chum, J. Matas, Matching with PROSAC - progressive sample consensus computer vision and pattern recognition. ,vol. 1, pp. 220- 226 ,(2005) , 10.1109/CVPR.2005.221
Yoav HaCohen, Eli Shechtman, Dan B. Goldman, Dani Lischinski, Non-rigid dense correspondence with applications for image enhancement ACM SIGGRAPH 2011 papers on - SIGGRAPH '11. ,vol. 30, pp. 70- ,(2011) , 10.1145/1964921.1964965
Rahul Raguram, Ondrej Chum, Marc Pollefeys, Jiri Matas, Jan-Michael Frahm, USAC: A Universal Framework for Random Sample Consensus IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 35, pp. 2022- 2038 ,(2013) , 10.1109/TPAMI.2012.257
Bruce D. Lucas, Takeo Kanade, An iterative image registration technique with an application to stereo vision international joint conference on artificial intelligence. pp. 674- 679 ,(1981)